Performance Analysis Of Morphological Operations in CPU and GPU for Accelerating Digital Image Applications
T.Kalaiselvi. International Journal of Computational Science and Information Technology (IJCSITY), 4 (1):
13(Februar 2016)
DOI: 10.5121/ijcsity.2016.4102
Zusammenfassung
In this paper, we evaluate the performance of morphological operations in central processing unit (CPU) and graphics processing unit (GPU) on various sizes of image and structuring element. The languages selected for algorithm implementation are C++, Matlab for CPU and CUDA for GPU. The parallel programming approach using threads for image analysis is done on basic entities of images. The morphological operations namely dilation and erosion are purely depends upon local neighborhood information of each pixel and thus independent.
%0 Journal Article
%1 noauthororeditor
%A T.Kalaiselvi,
%D 2016
%J International Journal of Computational Science and Information Technology (IJCSITY)
%K CUDA Dilation Erosion Graphics and processing unit
%N 1
%P 13
%R 10.5121/ijcsity.2016.4102
%T Performance Analysis Of Morphological Operations in CPU and GPU for Accelerating Digital Image Applications
%U http://aircconline.com/ijcsity/V4N1/4116ijcsity02.pdf
%V 4
%X In this paper, we evaluate the performance of morphological operations in central processing unit (CPU) and graphics processing unit (GPU) on various sizes of image and structuring element. The languages selected for algorithm implementation are C++, Matlab for CPU and CUDA for GPU. The parallel programming approach using threads for image analysis is done on basic entities of images. The morphological operations namely dilation and erosion are purely depends upon local neighborhood information of each pixel and thus independent.
@article{noauthororeditor,
abstract = {In this paper, we evaluate the performance of morphological operations in central processing unit (CPU) and graphics processing unit (GPU) on various sizes of image and structuring element. The languages selected for algorithm implementation are C++, Matlab for CPU and CUDA for GPU. The parallel programming approach using threads for image analysis is done on basic entities of images. The morphological operations namely dilation and erosion are purely depends upon local neighborhood information of each pixel and thus independent.},
added-at = {2018-08-07T08:03:31.000+0200},
author = {T.Kalaiselvi},
biburl = {https://www.bibsonomy.org/bibtex/2dda71d9bc001855016cdea364ee6c987/anderson_sam},
doi = {10.5121/ijcsity.2016.4102},
interhash = {eb990d11701d5a308bada681480cc93f},
intrahash = {dda71d9bc001855016cdea364ee6c987},
journal = {International Journal of Computational Science and Information Technology (IJCSITY) },
keywords = {CUDA Dilation Erosion Graphics and processing unit},
language = {english},
month = {February},
number = 1,
pages = 13,
timestamp = {2018-08-07T08:03:31.000+0200},
title = {Performance Analysis Of Morphological Operations in CPU and GPU for Accelerating Digital Image Applications },
url = {http://aircconline.com/ijcsity/V4N1/4116ijcsity02.pdf},
volume = 4,
year = 2016
}